@@ -8,14 +8,11 @@ export(BAG)

 export(BAGD)

 export(COUNT)

 export(DESC)

-export(DF)

 export(DG)

 export(DGE)

 export(DL)

 export(DLE)

 export(DOWN)

-export(EX)

-export(FN)

 export(MAX)

 export(MD)

 export(MEDIAN)

@@ -31,6 +28,7 @@ export(SUM)

 export(UP)

 export(compile_query)

 export(compile_query_fromfile)

+export(condition_evaluation)

 export(delete_dataset)

 export(download_as_GRangesList)

 export(download_dataset)

@@ -35,4 +35,8 @@ setMethod("show", "GMQLDataset",

                 cat(" value :",paste(object@value))

             })

+setGeneric("value", function(.dataset) standardGeneric("value"))

+

+setMethod("value", "GMQLDataset", function(.dataset) .dataset@value)

+

@@ -64,8 +64,19 @@

 # meta join condition

 .join_condition <- function(cond)

 {

-    join_condition_matrix <- do.call(rbind, cond)

-    join_condition_matrix

+    cond_matrix <- NULL

+    def <- cond$def

+    if(!is.null(def))

+        cond_matrix <- rbind(cond_matrix, def)

+    

+    exact <- cond$exact

+    if(!is.null(exact))

+        cond_matrix <- rbind(cond_matrix, exact)

+    

+    full <- cond$full

+    if(!is.null(full))

+        cond_matrix <- rbind(cond_matrix, full)

+    cond_matrix

 }

 .check_input <- function(value)

@@ -8,86 +8,57 @@

 #' They create a 2-D array made up by two coloumn:

 #' type of condition evaluation and the metadata attribute name

 #'

-#' \itemize{

-#' \item{FN: It defines a FULL (FULLNAME) evaluation of the input values.

+#'

+#' @param default series of string identifying a name of metadata attribute 

+#' to be evaluated.

+#' It defines a DEFAULT evaluation of the input values.

+#' DEFAULT evaluation: the two attributes match if both end with value.

+#' 

+#' @param full series of string identifying a name of metadata attribute 

+#' to be evaluated.

+#' It defines a FULL (FULLNAME) evaluation of the input values.

 #' FULL evaluation: two attributes match if they both end with value and,

-#' if they have further prefixes, the two prefix sequences are identical}

-#' \item{EX: It defines a EXACT evaluation of the input values.

+#' if they have further prefixes, the two prefix sequences are identical.

+#' 

+#' @param exact series of string identifying a name of metadata attribute 

+#' to be evaluated.

+#' It defines a EXACT evaluation of the input values.

 #' EXACT evaluation: only attributes exactly as value match; 

-#' no further prefixes are allowed. }

-#' \item{DF: It defines a DEFAULT evaluation of the input values.

-#' DEFAULT evaluation: the two attributes match if both end with value.}

-#' }

-#'

-#' @param ... series of string identifying a name of metadata attribute 

-#' to be evaluated

+#' no further prefixes are allowed. 

 #' 

-#' @return 2-D array containing method of evaluation and metadata

+#' @return list of 2-D array containing method of evaluation and metadata

 #' 

 #' @examples

 #' 

 #' "where is my example?"

 #' 

 #' @name Evaluation-Function

-#' @aliases FN

+#' @aliases condition_evaluation

 #' @rdname condition_eval_func

 #' @export

-FN <- function(...)

+condition_evaluation <- function(default = c(""), full = c(""), exact = c(""))

 {

-    conds <- c(...)

-    conds = conds[!conds %in% ""]

-    conds = conds[!duplicated(conds)]

-    if(length(conds)<=0)

-        join_condition_matrix <- .jnull("java/lang/String")

-    else

-    {

-        join_condition_matrix <- t(sapply(conds, function(x) {

-            new_value = c("FULL",x)

-            matrix <- matrix(new_value)

-        }))

-    }

-    join_condition_matrix

+    df <- .condition("DEF",default)

+    fn <- .condition("FULL",full)

+    ex <- .condition("EXACT",exact)

+    list("def" = df, "full" = fn, "exact" = ex)

 }

-#' @name Evaluation-Function

-#' @aliases EX

-#' @rdname condition_eval_func

-#' @export

-EX <- function(...)

+.condition <- function(cond, array)

 {

-    conds <- c(...)

-    conds = conds[!conds %in% ""]

-    conds = conds[!duplicated(conds)]

-    if(length(conds)<=0)

-        join_condition_matrix <- .jnull("java/lang/String")

+    array = array[!array %in% ""]

+    array = array[!duplicated(array)]

+    

+    if(!length(array))

+        join_condition_matrix <- NULL

     else

     {

-        join_condition_matrix <- t(sapply(conds, function(x) {

-            new_value = c("EXACT",x)

+        join_condition_matrix <- t(sapply(array, function(x) {

+            new_value = c(cond, x)

             matrix <- matrix(new_value)

         }))

     }

     join_condition_matrix

 }

-#' @name Evaluation-Function

-#' @aliases DF

-#' @rdname condition_eval_func

-#' @export

-DF <- function(...)

-{

-    conds <- c(...)

-    conds = conds[!conds %in% ""]

-    conds = conds[!duplicated(conds)]

-    if(length(conds)<=0)

-        join_condition_matrix <- .jnull("java/lang/String")

-    else

-    {

-        join_condition_matrix <- t(sapply(conds, function(x) {

-            new_value = c("DEF",x)

-            matrix <- matrix(new_value)

-        }))

-    }

-    join_condition_matrix

-}

@@ -64,9 +64,11 @@ filter_and_extract <- function(data, metadata = NULL,

                                 suffix = "antibody_target")

 {

     if(is(data,"GRangesList"))

-        .extract_from_GRangesList(data, metadata, metadata_prefix, regions)

+        .extract_from_GRangesList(data, metadata, metadata_prefix, regions, 

+                                    suffix)

     else

-        .extract_from_dataset(data, metadata, metadata_prefix, regions, suffix)

+        .extract_from_dataset(data, metadata, metadata_prefix, regions, 

+                                    suffix)

 }

 .extract_from_dataset <- function(datasetName, metadata, metadata_prefix, 

@@ -130,7 +132,7 @@ filter_and_extract <- function(data, metadata = NULL,

 }

 .extract_from_GRangesList <- function(rangesList, metadata, metadata_prefix, 

-                                        regions)

+                                        regions, suffix)

 {

     if(!is(rangesList,"GRangesList"))

         stop("only GrangesList admitted")

@@ -139,7 +141,8 @@ filter_and_extract <- function(data, metadata = NULL,

         stop("rangesList empty")

     meta_list <- metadata(rangesList)

-    samples <- .check_metadata_list(metadata, metadata_prefix,meta_list)

+    samples <- .check_metadata_list(metadata, metadata_prefix, meta_list, 

+                                        suffix)

     if(length(unlist(samples))<=0)

         samples <- rangesList

     else

@@ -166,7 +169,7 @@ filter_and_extract <- function(data, metadata = NULL,

     g1

 }

-.check_metadata_list <- function(metadata,metadata_prefix,meta_list)

+.check_metadata_list <- function(metadata,metadata_prefix,meta_list,col_name)

 {

     vec_meta <- paste0(metadata_prefix,metadata)

     list <- mapply(function(x,index){

@@ -48,16 +48,9 @@

 #' \item{an expression built using PARAMETER object: (ALL() + N) / K or

 #' ALL() / K, with N and K integer values  }

 #' }

-#' @param groupBy list of evalation functions to define evaluation on metadata:

-#' \itemize{

-#' \item{\code{\link{FN}}(value): Fullname evaluation, two attributes match 

-#' if they both end with \emph{value} and, if they have further prefixes,

-#' the two prefix sequence are identical}

-#' \item{\code{\link{EX}}(value): Exact evaluation, only attributes exactly 

-#' as \emph{value} match; no further prefixes are allowed. }

-#' \item{\code{\link{DF}}(value): Default evaluation, the two attributes match 

-#' if both end with \emph{value}.}

-#' }

+#' @param groupBy \code{\link{condition_evaluation}} function to support 

+#' methods with groupBy or JoinBy input paramter

+#' 

 #' @param ... a series of expressions separated by comma in the form 

 #' \emph{key} = \emph{aggregate}. The \emph{aggregate} is an object of 

 #' class AGGREGATES. The aggregate functions available are: \code{\link{SUM}}, 

@@ -122,7 +115,7 @@

 #' ## regions the minimum pvalue of the overlapping regions (min_pvalue) 

 #' ## and their Jaccard indexes (JaccardIntersect and JaccardResult).

 #' 

-#' res = cover(exp, 2, 3, groupBy = list(DF("cell")), 

+#' res = cover(exp, 2, 3, groupBy = condition_evaluation(c("cell")), 

 #' min_pValue = MIN("pvalue"))

 #' 

 #' @name cover

@@ -156,12 +149,15 @@ gmql_cover <- function(data, min_acc, max_acc, groupBy, aggregates, flag)

     if(!is.null(groupBy))

     {

         cond <- .join_condition(groupBy)

-        join_condition_matrix <- .jarray(cond, dispatch = TRUE)

+        if(is.null(cond))

+            join_condition_matrix <- .jnull("java/lang/String")

+        else

+            join_condition_matrix <- .jarray(cond, dispatch = TRUE)

     }

     else

         join_condition_matrix <- .jnull("java/lang/String")

-    if(!is.null(aggregates) && !length(aggregates) == 0)

+    if(!is.null(aggregates) && length(aggregates))

     {

         aggr <- .aggregates(aggregates,"AGGREGATES")

         metadata_matrix <- .jarray(aggr, dispatch = TRUE)

@@ -24,16 +24,8 @@

 #' \code{\link{DLE}}, \code{\link{DGE}}, \code{\link{DL}}, \code{\link{DG}},

 #' \code{\link{MD}}, \code{\link{UP}}, \code{\link{DOWN}}

 #' 

-#' @param joinBy list of evalation functions to define evaluation on metadata:

-#' \itemize{

-#' \item{ \code{\link{FN}}(value): Fullname evaluation, two attributes match 

-#' if they both end with \emph{value} and, if they have further prefixes,

-#' the two prefix sequence are identical.}

-#' \item{ \code{\link{EX}}(value): Exact evaluation, only attributes exactly 

-#' as \emph{value} match; no further prefixes are allowed.}

-#' \item{ \code{\link{DF}}(value): Default evaluation, the two attributes match 

-#' if both end with \emph{value}.}

-#' }

+#' @param joinBy \code{\link{condition_evaluation}} function to support 

+#' methods with groupBy or JoinBy input paramter

 #' 

 #' @param region_output single string that declares which region is given in 

 #' output for each input pair of left dataset and right dataset regions 

@@ -93,7 +85,6 @@ setMethod("merge", c("GMQLDataset","GMQLDataset"),

                 {

                     ptr_data_x <- x@value

                     ptr_data_y <- y@value

-                    joinBy = list(...)

                     gmql_join(ptr_data_x, ptr_data_y, genometric_predicate, 

                                 joinBy, region_output)

                 })

@@ -123,17 +114,20 @@ gmql_join <- function(left_data, right_data, genometric_predicate, joinBy,

     else

         genomatrix <- .jnull("java/lang/String")

-    if(!is.null(joinBy) && !length(joinBy) == 0)

-        join_condition_matrix <- .jarray(.join_condition(joinBy), 

-                                            dispatch = TRUE)

+    if(!is.null(joinBy))

+    {

+        cond <- .join_condition(joinBy)

+        if(is.null(cond))

+            join_condition_matrix <- .jnull("java/lang/String")

+        else

+            join_condition_matrix <- .jarray(cond, dispatch = TRUE)

+    }

     else

         join_condition_matrix <- .jnull("java/lang/String")

     ouput <- toupper(region_output)

-    if(!identical(ouput,"CAT") && !identical(ouput,"LEFT") && 

-        !identical(ouput,"RIGHT") && !identical(ouput,"INT") && 

-        !identical(ouput,"RIGHT_DIST") && !identical(ouput,"BOTH") &&

-        !identical(ouput,"LEFT_DIST"))

+    if(!ouput %in% c("CAT", "LEFT", "RIGHT", "INT", "BOTH", "RIGHT_DIST", 

+                        "LEFT_DIST"))

         stop("region_output must be cat, left, right, right_dist, left_dist 

                 or int (intersection)")

@@ -15,16 +15,8 @@

 #' @importFrom S4Vectors aggregate

 #'

 #' @param x GMQLDataset class object

-#' @param groupBy list of evalation functions to define evaluation on metadata:

-#' \itemize{

-#' \item{\code{\link{FN}}(value): Fullname evaluation, two attributes match 

-#' if they both end with \emph{value} and, if they have further prefixes,

-#' the two prefix sequences are identical}

-#' \item{\code{\link{EX}}(value): Exact evaluation, only attributes exactly 

-#' as \emph{value} match; no further prefixes are allowed. }

-#' \item{\code{\link{DF}}(value): Default evaluation, the two attributes match 

-#' if both end with \emph{value}.}

-#' }

+#' @param groupBy \code{\link{condition_evaluation}} function to support 

+#' methods with groupBy or JoinBy input paramter

 #' 

 #' @return GMQLDataset object. It contains the value to use as input 

 #' for the subsequent GMQLDataset method

@@ -48,7 +40,7 @@

 #' ## antibody_target and cell metadata

 #' ## attributes.

 #'

-#' merged = aggregate(exp, list(DF("antibody_target","cell")))

+#' merged = aggregate(exp, condition_evaluation(c("antibody_target","cell")))

 #'

 #' @name aggregate

 #' @rdname aggregate

@@ -65,13 +57,13 @@ setMethod("aggregate", "GMQLDataset",

 gmql_merge <- function(input_data, groupBy)

 {

-    if(!is.list(groupBy))

-        stop("groupBy must be list")

-    

-    if(!is.null(groupBy) && !length(groupBy) == 0)

+    if(!is.null(groupBy))

     {

         cond <- .join_condition(groupBy)

-        join_condition_matrix <- .jarray(cond, dispatch = TRUE)

+        if(is.null(cond))

+            join_condition_matrix <- .jnull("java/lang/String")

+        else

+            join_condition_matrix <- .jarray(cond, dispatch = TRUE)

     }

     else

         join_condition_matrix <- .jnull("java/lang/String")

@@ -53,8 +53,9 @@

 setMethod("union", c("GMQLDataset","GMQLDataset"),

             function(x, y)

             {

-                ptr_data_x = x@value

-                ptr_data_y = y@value

+                

+                ptr_data_x = value(x)

+                ptr_data_y = value(y)

                 gmql_union(ptr_data_x, ptr_data_y)

             })

@@ -319,7 +319,7 @@ run_query <- function(url, queryName, query, output_gtf = TRUE)

     req <- httr::GET(url)

     real_URL <- req$url

-    URL <- paste0(real_URL,"queries/run/",fileName,"/",out)

+    URL <- paste0(real_URL,"queries/run/",queryName,"/",out)

     h <- c('Accept' = "Application/json",

                 'Content-Type' = 'text/plain','X-Auth-Token' = authToken)

Binary files a/inst/java/GMQL.jar and b/inst/java/GMQL.jar differ

@@ -7,6 +7,8 @@

 \alias{EX}

 \alias{Evaluation-Function}

 \alias{DF}

+\alias{Evaluation-Function}

+\alias{condition_evaluation}

 \title{Condition evaluation functions}

 \usage{

 FN(...)

@@ -14,6 +16,8 @@ FN(...)

 EX(...)

 DF(...)

+

+condition_evaluation(...)

 }

 \arguments{

 \item{...}{series of string identifying a name of metadata attribute 

@@ -18,9 +18,9 @@ this condition is logically "ANDed" with prefix filtering (see below)

 if NULL no filtering action occures

 (i.e every sample is taken for region filtering)}

-\item{metadata_prefix}{vector of strings that will filter metadata

-containing rispectively every element of this vector.

-number of element in both vector must match}

+\item{metadata_prefix}{vector of strings that will support the metadata

+filtering. If defined every defined 'metadata' are concatenated with the 

+corresponding prefix.}

 \item{regions}{vector of strings that extracts only region attribute 

 specified; if NULL no regions attribute is taken and the output is only 

@@ -33,7 +33,7 @@ metadata() associated. If not present, the column name is the name of

 selected regions}

 }

 \value{

-Granges with selected regions (if any) in elementMetadata

+GRanges with selected regions

 }

 \description{

 This function lets user to create a new GRangesList with fixed information:

@@ -44,15 +44,23 @@ with its prefix. The input regions are shown for each sample obtained

 from filtering.

 }

 \details{

-This function works only with datatset or GRangesList that has the same

-information about regions attribute (but of course different value)

+This function works only with datatset or GRangesList which samples or 

+Granges have the same regions coordinates (chr, ranges, strand)

+

 In case of Grangeslist data input the function will search for metadata

 into metadata() function associated to Grangeslist.

 }

 \examples{

+## This statement defines the path to the folders "DATASET" in the 

+## subdirectory "example" of the package "RGMQL" and filter such folder 

+## dataset including at output only "pvalue" and "peak" regions

+

 test_path <- system.file("example", "DATASET", package = "RGMQL")

-filter_and_extract(test_path,regions = c("pvalue", "peak"))

+filter_and_extract(test_path, regions = c("pvalue", "peak"))

+

+## This statement import a GMQL dataset as GRangesList and filter it 

+## including at output only "pvalue" and "peak" regions

 grl = import_gmql(test_path, TRUE)

 filter_and_extract(grl, regions = c("pvalue", "peak"))

@@ -41,6 +41,7 @@ If error occurs, a specific error is printed

 \examples{

 \dontrun{

+

 remote_url = "http://genomic.deib.polimi.it/gmql-rest-r/"

 login_gmql(remote_url)

 run_query(remote_url, "query_1", "DATASET = SELECT() Example_Dataset1;

@@ -48,7 +49,7 @@ MATERIALIZE DATASET INTO RESULT_DS;", output_gtf = FALSE)

 test_path <- system.file("example", package = "RGMQL")

 test_query <- file.path(test_path, "query1.txt")

-run_query_fromfile(remote_url, "query_1", test_query, output_gtf = FALSE)

+run_query_fromfile(remote_url, test_query, output_gtf = FALSE)

 }

 }

@@ -50,7 +50,7 @@ only those samples that have the same value for each attribute

 are considered when performing the difference.

 }

 \examples{

-## Thi statement initializes and runs the GMQL server for local execution 

+## This statement initializes and runs the GMQL server for local execution 

 ## and creation of results on disk. Then, with system.file() it defines 

 ## the path to the folders "DATASET" and "DATASET_GDM" in the subdirectory 

 ## "example" of the package "RGMQL" and opens such folder as a GMQL 

@@ -3,7 +3,7 @@

 \name{show_dataset}

 \alias{show_dataset}

 \alias{show_datasets_list}

-\title{Show Datasets}

+\title{Show datasets}

 \usage{

 show_datasets_list(url)

 }

@@ -12,20 +12,18 @@ show_datasets_list(url)

 and base url; service name is added automatically}

 }

 \value{

-list of datasets.

-

-Every dataset in the list is identified by:

+List of datasets. Every dataset in the list is identified by:

 \itemize{

 \item{name: name of dataset}

 \item{owner: public or name of the user}

 }

 }

 \description{

-It show all GMQL dataset stored in repository using the proper GMQL 

-web service available on a remote server

+It shows all GMQL datasets stored in remote repository using the proper 

+GMQL web service available on a remote server

 }

 \details{

-If error occures a specific error is printed

+If error occurs, a specific error is printed

 }

 \examples{

@@ -11,18 +11,17 @@ show_jobs_list(url)

 and base url; service name is added automatically}

 }

 \value{

-list of jobs

-Every job in the list is identified by:

+List of jobs. Every job in the list is identified by:

 \itemize{

 \item{id: unique job identifier}

 }

 }

 \description{

-It show all Jobs (run, succeded or failed) invoked by user using the proper 

+It shows all jobs (run, succeded or failed) invoked by user using the proper 

 GMQL web service available on a remote server

 }

 \details{

-If error occurs a specific error is printed

+If error occurs, a specific error is printed

 }

 \examples{

 remote_url = "http://genomic.deib.polimi.it/gmql-rest-r"

@@ -11,19 +11,18 @@ show_queries_list(url)

 and base url; service name is added automatically}

 }

 \value{

-list of queries

-Every query in the list is identified by:

+list of queries. Every query in the list is identified by:

 \itemize{

 \item{name: name of query}

 \item{text: text of GMQL query}

 }

 }

 \description{

-It shows all the GMQL query saved on repository using the proper GMQL 

-web service available on a remote server

+It shows all the GMQL queries saved on remote repository using the proper 

+GMQL web service available on a remote server

 }

 \details{

-if error occures, a specific error is printed

+If error occurs, a specific error is printed

 }

 \examples{

@@ -12,12 +12,11 @@ and base url; service name is added automatically}

 \item{datasetName}{name of dataset to get

 if the dataset is a public dataset, we have to add "public." as prefix, 

-as shown in the example below otherwise no prefix is needed}

+as shown in the example below, otherwise no prefix is needed}

 }

 \value{

-list of samples in dataset.

-

-Every sample in the list is identified by:

+List of samples in dataset. Every sample in the list is identified 

+by:

 \itemize{

 \item{id: id of sample}

 \item{name: name of sample}

@@ -29,12 +28,17 @@ It show all sample from a specific GMQL dataset using the proper

 GMQL web service available on a remote server

 }

 \details{

-If error occures a specific error is printed

+If error occurs, a specific error is printed

 }

 \examples{

+## Login to GMQL REST services suite as guest

+

 remote_url = "http://genomic.deib.polimi.it/gmql-rest-r"

 login_gmql(remote_url)

-list <- show_samples_list(remote_url, "public.HG19_BED_ANNOTATION")

+

+## It show all sample present into public dataset 'Example_Dataset1'

+

+list <- show_samples_list(remote_url, "public.Example_Dataset1")

 }

@@ -290,45 +290,45 @@ with at least one mutation. Return the list of samples ordered by

 the number of such exons.

 ```{r, query, eval = TRUE}

-## These statement defines the path to the folders "EXON" and "MUT" in the 

-## subdirectory "example" of the package "RGMQL"

+# These statement defines the path to the folders "EXON" and "MUT" in the 

+# subdirectory "example" of the package "RGMQL"

 exon_path <- system.file("example", "EXON", package = "RGMQL")

 mut_path <- system.file("example", "MUT", package = "RGMQL")

-## Read EXON folder as a GMQL dataset named "exon_ds" containing a single 

-## sample with exon regions and MUT folder as a GMQL dataset named "mut_ds" 

-## containing multiple samples with mutation regions

+# Read EXON folder as a GMQL dataset named "exon_ds" containing a single 

+# sample with exon regions and MUT folder as a GMQL dataset named "mut_ds" 

+# containing multiple samples with mutation regions

 exon_ds  <- read_dataset(exon_path)

 mut_ds  <- read_dataset(mut_path)

-## Filter out mut_ds based on predicate 

+# Filter out mut_ds based on predicate 

 mut = filter(mut_ds, manually_curated__dataType == 'dnaseq' & 

                 clinical_patient__tumor_tissue_site == 'breast')

-## Filter out exon_ds based on predicate 

+# Filter out exon_ds based on predicate 

 exon =  filter(exon_ds, annotation_type == 'exons' & 

                     original_provider == 'RefSeq')

-## For each mutation sample, count mutations within each exon while 

-## mapping the mutations to the exon regions using the map() function 

+# For each mutation sample, count mutations within each exon while 

+# mapping the mutations to the exon regions using the map() function 

 exon1 <- map(exon, mut)

-## Remove exons in each sample that do not contain mutations

+# Remove exons in each sample that do not contain mutations

 exon2 <- filter(exon1, count_Exon_Mut >= 1)

-## Using the extend() function, count how many exons remain in each sample and

-## store the result in the sample metadata as a new attribute???value pair, 

-## with exon_count as attribute name 

+# Using the extend() function, count how many exons remain in each sample and

+# store the result in the sample metadata as a new attribute???value pair, 

+# with exon_count as attribute name 

 exon3 <- extend(exon2, exon_count = COUNT())

-## Order samples in descending order of the added metadata exon_count 

+# Order samples in descending order of the added metadata exon_count 

 exon_res = arrange(exon3, list(DESC("exon_count")))

 ```

@@ -336,7 +336,8 @@ exon_res = arrange(exon3, list(DESC("exon_count")))

 If you want to store persistently the result, you can materialize it into 

 specific path defined as input parameter.

 ```{r, materialize, eval = TRUE}

-## Materialize the result dataset on disk

+# Materialize the result dataset on disk

+

 collect(exon_res)

 ```

 by default *collect()* has R workig directoy as stored path and *ds1* as name 

@@ -474,38 +475,38 @@ in this way login is automatically performed as specified above

 After init, we can start building our queries:

 ```{r, remote query, eval = TRUE}

-## Read the remote dataset HG19_TCGA_dnaseq 

-## Read the remote dataset HG19_BED_ANNOTATION 

+# Read the remote dataset HG19_TCGA_dnaseq 

+# Read the remote dataset HG19_BED_ANNOTATION 

 TCGA_dnaseq  <- read_dataset("public.HG19_TCGA_dnaseq",is_local = FALSE)

 HG19_bed_ann  <- read_dataset("public.HG19_BED_ANNOTATION",is_local = FALSE)

-## Filter out HG19_bed_ann based on predicate 

+# Filter out HG19_bed_ann based on predicate 

 mut = filter(HG19_bed_ann, manually_curated__dataType == 'dnaseq' & 

                 clinical_patient__tumor_tissue_site == 'breast')

-## Filter out TCGA_dnaseq based on predicate 

+# Filter out TCGA_dnaseq based on predicate 

 exon =  filter(TCGA_dnaseq, annotation_type == 'exons' & 

                     original_provider == 'RefSeq')

-## For each mutation sample, count mutations within each exon while 

-## mapping the mutations to the exon regions using the map() function 

+# For each mutation sample, count mutations within each exon while 

+# mapping the mutations to the exon regions using the map() function 

 exon1 <- map(exon, mut)

-## Remove exons in each sample that do not contain mutations

+# Remove exons in each sample that do not contain mutations

 exon2 <- filter(exon1, count_Exon_Mut >= 1)

-## Using the extend() function, count how many exons remain in each sample and

-## store the result in the sample metadata as a new attribute???value pair, 

-## with exon_count as attribute name 

+# Using the extend() function, count how many exons remain in each sample and

+# store the result in the sample metadata as a new attribute???value pair, 

+# with exon_count as attribute name 

 exon3 <- extend(exon2, exon_count = COUNT())

-## Order samples in descending order of the added metadata exon_count 

+# Order samples in descending order of the added metadata exon_count 

 exon_res = arrange(exon3,list(DESC("exon_count")))

 ```

@@ -534,21 +535,21 @@ even in the same query as in the following example:

 ```{r, mixed query, eval = TRUE}

-## This statement defines the path to the folder "EXON" in the subdirectory 

-## "example" of the package "RGMQL"

+# This statement defines the path to the folder "EXON" in the subdirectory 

+# "example" of the package "RGMQL"

 exon_path <- system.file("example", "EXON", package = "RGMQL")

-## Read EXON folder as a GMQL dataset named "exon_ds" containing a single 

-## sample with exon regions

+# Read EXON folder as a GMQL dataset named "exon_ds" containing a single 

+# sample with exon regions

 exon_ds  <- read_dataset(exon_path,is_local = TRUE)

-## Read the remote dataset HG19_BED_ANNOTATION 

+# Read the remote dataset HG19_BED_ANNOTATION 

 HG19_bed_ann  <- read_dataset("public.HG19_BED_ANNOTATION",is_local = FALSE)

-## Filter out based on predicate

+# Filter out based on predicate

 mut = filter(HG19_bed_ann, manually_curated__dataType == 'dnaseq' & 

                 clinical_patient__tumor_tissue_site == 'breast')

@@ -556,22 +557,22 @@ mut = filter(HG19_bed_ann, manually_curated__dataType == 'dnaseq' &

 exon =  filter(exon_ds, annotation_type == 'exons' & 

                     original_provider == 'RefSeq')

-## For each mutation sample, count mutations within each exon while 

-## mapping the mutations to the exon regions using the map() function 

+# For each mutation sample, count mutations within each exon while 

+# mapping the mutations to the exon regions using the map() function 

 exon1 <- map(exon, mut)

-## Remove exons in each sample that do not contain mutations

+# Remove exons in each sample that do not contain mutations

 exon2 <- filter(exon1, count_Exon_Mut >= 1)

-## Using the extend() function, count how many exons remain in each sample and

-## store the result in the sample metadata as a new attribute???value pair, 

-## with exon_count as attribute name 

+# Using the extend() function, count how many exons remain in each sample and

+# store the result in the sample metadata as a new attribute???value pair, 

+# with exon_count as attribute name 

 exon3 <- extend(exon2, exon_count = COUNT())

-## Order samples in descending order of the added metadata exon_count 

+# Order samples in descending order of the added metadata exon_count 

 exon_res = arrange(exon3,list(DESC("exon_count")))

@@ -607,8 +608,8 @@ if present, as data structure suitable to further processing in other packages.

 We can import a GMQL dataset into R environment as follows:

 ```{r, import, eval = TRUE}

-## This statement defines the path to the folder "EXON" in the subdirectory 

-## "example" of the package "RGMQL"

+# This statement defines the path to the folder "EXON" in the subdirectory 

+# "example" of the package "RGMQL"

 dataset_path <- system.file("example", "EXON", package = "RGMQL")

@@ -621,8 +622,8 @@ the second parameter *is_gtf* must specifies the file format: .GTF or .GDM.

 We can export a GRangesList as GMQL dataset as follows:

 ```{r, export, eval = TRUE}

-## This statement defines the path to  the subdirectory "example" of the 

-## package "RGMQL"

+# This statement defines the path to  the subdirectory "example" of the 

+# package "RGMQL"

 dir_out <- system.file("example", package = "RGMQL")

@@ -638,8 +639,8 @@ the second parameter *is_gtf* specifies the file format: .GTF or .GDM.

 We can also import only a part of a GMQL dataset into R environment, 

 by filtering its content as follows:

 ```{r, filter_extract, eval = TRUE}

-## This statement defines the path to the folder "TEAD" in the subdirectory 

-## "example" of the package "RGMQL"

+# This statement defines the path to the folder "TEAD" in the subdirectory 

+# "example" of the package "RGMQL"

 data_in <- system.file("example", "TEAD", package = "RGMQL")